So people are freaking out about the polls. There was a Pew poll that seemed pretty good for Romney, and the same was true of a DailyKos poll.
I have something that's going to make everyone feel better, and that something is called Math. The math says that Romney has had a bounce, but that Barack Obama is still winning.
Follow me over the great orange swirl for more.
First, I'm going to quote what Nate Silver had to say about the Pew poll.
[I]s it really likely that Mr. Romney leads the race by 4 points right now? The consensus of the evidence, particularly the national tracking polls, would suggest otherwise. Instead, the forecast model’s conclusion is that the whole of the data is still consistent with a very narrow lead for Mr. Obama, albeit one that is considerably diminished since Denver.
It might be granted that the situation is more ambiguous than usual right now. But our forecast model looks at literally all of the polls; it estimates Mr. Romney’s post-debate bounce as being 2.5 percentage points, not quite enough to erase Mr. Obama’s pre-debate advantage...
The last thing to consider is that the fundamentals of the race aren’t consistent with a 4-point lead for Mr. Romney. Instead, the most recent economic numbers, and Mr. Obama’s approval ratings, would seem to point to an election in which he is the slight favorite. We don’t use approval ratings in our forecast, but we do use the economic data, and both the monthly payrolls report and the broader FiveThirtyEight economic index would point toward an election in which Mr. Obama is favored in the popular vote by around 2.5 percentage points.
So that's my three paragraph limit for quoting, and if you want more you should go read what Nate
has to say.
Let's look at what Markos has to say about the Daily Kos poll. He pointed out that the poll was conducted at the height of the post-debate bounce.
PPP does call-backs: It identifies a random range of numbers and begins calling them on Thursday. If they get no answer, they keep trying the same numbers on subsequent days until they get the required number of responses (we ask for at least 1,000). This avoids the old tropes about young liberals being out partying on Friday nights, while conservatives are at church on Sunday mornings, etc.
So this week, 47 percent of responses were on Thursday, 28 percent on Friday, 17 percent on Saturday, and just 8 percent on Sunday. Romney won Thursday 49-48 and Friday 49-44 before losing steam over the weekend. While Romney won Thursday and Friday by a combined 2.5 points, he won Saturday and Sunday by just 0.5 percent.
Nate Silver says that there's a lot to what Markos says here, and that this is a valid critique of the poll data.
You cannot take one poll, or two or three polls, completely out of context and think that you understand what's going on. One poll is mathematically meaningless. Five polls start to give you a better picture. 50 or 60 polls start showing you what things might actually look like, and that is why I trust Nate Silver: he's aggregating all of the data into a big picture.
This is really important. If you don't understand that one or two data points are statistically meaningless, then you don't understand statistical data collection like polling.
Here is where I start getting furious with some of my fellow Liberals when we talk about math and science. If a single study comes out showing that green beans are actually red, some people will assume that the study is the Word of God, when it is in fact one study. Science being what it is, there will eventually be a consensus of studies proving that green beans are in fact green. The one "red" study, or even two or three studies in question are called outliers.
Two polls conducted immediately after the terrible horrible no good very bad debate which show a pretty clear Romney bounce are not all of the evidence, or even most of the evidence. They are two data points that seem to be outliers when compared with the rest of the polling.
Or to put that another way, even Rasmussen doesn't show that big of a bounce for Romney. These polls are so good for Romney that they are outshining Rasmussen, and that's a good sign that they're outliers. Other polls coming out show pretty clearly that there is not a +4 bounce for Romney.
Let's take a look at a group of swing state polls that came out on the same day:
Now lets look at the TPM poll tracker, which currently puts Romney up two points:
See all those dots way up high and way down low? That's statistical noise, and the dots that are way far in either direction are outliers. But let me show you another thing that you're missing when you look at that data. It's a couple of graphics down and to the right from the TPM polltracker:
The same data that shows Mitt Romney ahead shows Barack Obama winning the election with 270 electoral votes.
Polls don't exist in a vacuum. You have to look at every single poll. You have to extrapolate the national polls based on data from state polls. You have to look at national polls and fill in the gaps in your state polling. You have to account for when the polls were conducted, such as in the middle of the moment when Americans have felt better about Mitt Romney than at any other time in polling history.
It's going to take polling into next week to see what happens. Yeah, the polls could have tightened. That's what I think is happening: conservatives are pulling themselves together and starting to actually fight us. We're going to see some poll tightening because of that.
It's also possible that this is Romney's dead cat bounce, and will be the high water mark on the Romney campaign, but I don't like making predictions like that, even when I hope they're true.
What I can say is that all is not lost. Barack Obama is still winning this election, which will come down to, as it always does, who gets their people to the polls.
That's how elections are won, by volunteers running the ground game and getting people to the polls. We have a huge advantage when it comes to a fired up, activated base.
The math says Obama is still winning, because Barack Obama is still winning in the swing state polls. That's not something that can really be debated, that's a mathematical fact. In order to keep that a mathematical fact we need to keep working on getting out the vote.
If we make phone calls, knock on doors, and keep fighting, we will win this thing.
And the republican party knows it, which is why there are so many concern trolls bouncing around trying to convince us that there's nothing we can do, and that all is lost, because they want to shake up our ground game.
We need to keep doing what we've been doing. This election is ours to win Kossacks, and we're still winning it. We just have to keep on trucking and not let our morale collapse because some people are having an unwarranted freakout over two data points that aren't in step with the rest of the data.
Click the poster to volunteer.